From 4e3b43f18046538171928256acefd01d97eed0ae Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Mon, 5 Feb 2018 16:46:06 +1000 Subject: [PATCH] r600/atomic: fix ATOMCAS instruction. This has 4 srcs. This fixes: KHR-GL45.shader_atomic_counter_ops_tests.ShaderAtomicCounterOpsExchangeTestCase Reviewed-by: Roland Scheidegger Signed-off-by: Dave Airlie --- src/gallium/drivers/r600/r600_shader.c | 32 +++++++++++++++++++++++++- 1 file changed, 31 insertions(+), 1 deletion(-) diff --git a/src/gallium/drivers/r600/r600_shader.c b/src/gallium/drivers/r600/r600_shader.c index 4874d14a581..08bc1484793 100644 --- a/src/gallium/drivers/r600/r600_shader.c +++ b/src/gallium/drivers/r600/r600_shader.c @@ -8680,6 +8680,33 @@ static int tgsi_atomic_op_gds(struct r600_shader_ctx *ctx) if (r) return r; + if (gds_op == FETCH_OP_GDS_CMP_XCHG_RET) { + if (inst->Src[3].Register.File == TGSI_FILE_IMMEDIATE) { + int value = (ctx->literals[4 * inst->Src[3].Register.Index + inst->Src[3].Register.SwizzleX]); + memset(&alu, 0, sizeof(struct r600_bytecode_alu)); + alu.op = ALU_OP1_MOV; + alu.dst.sel = ctx->temp_reg; + alu.dst.chan = is_cm ? 2 : 1; + alu.src[0].sel = V_SQ_ALU_SRC_LITERAL; + alu.src[0].value = value; + alu.last = 1; + alu.dst.write = 1; + r = r600_bytecode_add_alu(ctx->bc, &alu); + if (r) + return r; + } else { + memset(&alu, 0, sizeof(struct r600_bytecode_alu)); + alu.op = ALU_OP1_MOV; + alu.dst.sel = ctx->temp_reg; + alu.dst.chan = is_cm ? 2 : 1; + r600_bytecode_src(&alu.src[0], &ctx->src[3], 0); + alu.last = 1; + alu.dst.write = 1; + r = r600_bytecode_add_alu(ctx->bc, &alu); + if (r) + return r; + } + } if (inst->Src[2].Register.File == TGSI_FILE_IMMEDIATE) { int value = (ctx->literals[4 * inst->Src[2].Register.Index + inst->Src[2].Register.SwizzleX]); int abs_value = abs(value); @@ -8719,7 +8746,10 @@ static int tgsi_atomic_op_gds(struct r600_shader_ctx *ctx) gds.src_gpr2 = 0; gds.src_sel_x = is_cm ? 0 : 4; gds.src_sel_y = is_cm ? 1 : 0; - gds.src_sel_z = 7; + if (gds_op == FETCH_OP_GDS_CMP_XCHG_RET) + gds.src_sel_z = is_cm ? 2 : 1; + else + gds.src_sel_z = 7; gds.dst_sel_x = 0; gds.dst_sel_y = 7; gds.dst_sel_z = 7; -- 2.30.2